def __init__(self):
self.settings = Settings.getInstance()
self.debug = self.settings.debug
self.htmlRetriever = HtmlRetriever.getInstance(self.settings.use_proxy)
if self.settings.save_pdflink:
self.pdfcache = PDFLinkSaver.getInstance()
self.author = re.compile('<div class="?gs_a"?>([^\\x00]+?) - ', re.I)
self.pdf_block = re.compile('<div class="?gs_ggs gs_fl"?><a href="?([^\s"]+)?"?[^>]+?><span class="?gs_ctg2"?>\[PDF\]</span>', re.I)
self.citation_block = re.compile('<div class="?gs_fl"?>.*?</div>', re.I)
def __init__(self):
self.settings = Settings.getInstance()
self.debug = self.settings.debug
self.htmlRetriever = HtmlRetriever.getInstance(self.settings.use_proxy)
if self.settings.save_pdflink:
self.pdfcache = PDFLinkSaver.getInstance()
self.author = re.compile('<div class="?gs_a"?>([^\\x00]+?) - ', re.I)
self.pdf_block = re.compile(
'<div class="?gs_ggs gs_fl"?><a href="?([^\s"]+)?"?[^>]+?><span class="?gs_ctg2"?>\[PDF\]</span>',
re.I)
self.citation_block = re.compile('<div class="?gs_fl"?>.*?</div>',
re.I)
def __init__(self):
print "Task: extract paper's citation from schooler.google.com.\n"
self.settings = Settings.getInstance()
self.debug = self.settings.debug
# Configs
self.mgr_interval = 10 # seconds
self.max_person_thread = 2 # max threads used to extract person,
self.max_pub_thread = 2 # these 2 values can modified on the fly. diff in day or night
# Threads and configurations
self.t_mgr = None # MgrThread(self) # management thread, create
self.t_provider = None
self.person_thread_pool = [
] #= Queue.Queue(maxsize=self.max_person_thread)
self.pub_thread_pool = [] #= Queue.Queue(maxsize=self.max_pub_thread)
self.busy_semaphore = 0 # 用来监视是否所有的线程都处于Idle状态
self.busy_semaphore_lock = threading.Lock() # 用来监视是否所有的线程都处于Idle状态
# utils
self.store = None
# switchers & flags
self.running = True # If False, threads will stop after current task.
self.stopped = False # If MGRThread can stop.
self.pause = False # All works paused.
self.waiting_to_finish = False # No additional data. all added to queue.
self.num_report = 0
self.last_report_time = datetime.datetime.now() # 上次Interval的时间
self.restart_all_thread = False
self.detect_exit_wait = 0 # 当刚刚从pause模式退出来时，会有大量failed的任务，会导致立刻再次等待
self.generation = 0
self.dao = dbs()
self.personDao = PersonDao()
self.pubDao = PublicationDao()
if self.settings.save_pdflink:
self.pdfcache = PDFLinkSaver.getInstance()
# start
self.determineGereration()
def __init__(self):
print "Task: extract paper's citation from schooler.google.com.\n"
self.settings = Settings.getInstance()
self.debug = self.settings.debug
# Configs
self.mgr_interval = 10 # seconds
self.max_person_thread = 2 # max threads used to extract person,
self.max_pub_thread = 2 # these 2 values can modified on the fly. diff in day or night
# Threads and configurations
self.t_mgr = None # MgrThread(self) # management thread, create
self.t_provider = None
self.person_thread_pool = [] # = Queue.Queue(maxsize=self.max_person_thread)
self.pub_thread_pool = [] # = Queue.Queue(maxsize=self.max_pub_thread)
self.busy_semaphore = 0 # 用来监视是否所有的线程都处于Idle状态
self.busy_semaphore_lock = threading.Lock() # 用来监视是否所有的线程都处于Idle状态
# utils
self.store = None
# switchers & flags
self.running = True # If False, threads will stop after current task.
self.stopped = False # If MGRThread can stop.
self.pause = False # All works paused.
self.waiting_to_finish = False # No additional data. all added to queue.
self.num_report = 0
self.last_report_time = datetime.datetime.now() # 上次Interval的时间
self.restart_all_thread = False
self.detect_exit_wait = 0 # 当刚刚从pause模式退出来时，会有大量failed的任务，会导致立刻再次等待
self.generation = 0
self.dao = dbs()
self.personDao = PersonDao()
self.pubDao = PublicationDao()
if self.settings.save_pdflink:
self.pdfcache = PDFLinkSaver.getInstance()
# start
self.determineGereration()
for key, models in all_models.items(): print key for model in models: print "\t", model else: print 'all_models is None' print '- all_models end ----------------------\n' (pubs_found, pubs_notfound) = PubMatcher.getInstance().matchPub(used_pubs, all_models) for pub in pubs_found: print 'pubs found' , pub print '-' * 100 for pub in pubs_notfound: print 'not found' , pub print '- test done -' if __name__ == '__main__': ''' top pub person， this is in local database. ''' debug = DebugSuit() # debug.debug_person(29463, 'Reihaneh Safavi-Naini', 4) debug.debug_pubs() # end if Settings.getInstance().save_pdflink: PDFLinkSaver.getInstance().flush()
print '\n- all_models ----------------------'
if all_models is not None:
for key, models in all_models.items():
print key
for model in models:
print "\t", model
else:
print 'all_models is None'
print '- all_models end ----------------------\n'
(pubs_found, pubs_notfound) = PubMatcher.getInstance().matchPub(
used_pubs, all_models)
for pub in pubs_found:
print 'pubs found', pub
print '-' * 100
for pub in pubs_notfound:
print 'not found', pub
print '- test done -'
if __name__ == '__main__':
''' top pub person， this is in local database.
'''
debug = DebugSuit()
# debug.debug_person(29463, 'Reihaneh Safavi-Naini', 4)
debug.debug_pubs()
# end
if Settings.getInstance().save_pdflink:
PDFLinkSaver.getInstance().flush()
